Vfrdtyky

text = "Lorem ipsum dolor sit amet,n consectetur adipiscing elit,nsed do eiusmod tempor incididuntnut labore et dolore magna aliqua.nUt enim ad minim veniam,nquis nostrud exercitation ullamco laboris nisinut aliquip ex ea commodo consequat.nDuis aute irure dolor in reprehenderit in voluptate velit essencillum dolore eu fugiat nulla pariatur.nExcepteur sint occaecat cupidatat non proident,nLorem ipsum dolor sit amet etwas,nsunt in culpa qui officia deserunt mollit anim id est laborum"



// to map a text to sentences and tokens

text2SentencesTokens = function(text) {

  var self = this;

  return new Promise((resolve, _) => {

    let sentences = text.split(/n+/g);

    let sentencesP = sentences.map((sentence, lineIndex) => { // for each sentence

      return new Promise((resolve, _) => {

        let tokens = sentence.split(/s+/g);

        let tokensP = tokens.map((token, tokenIndex) => { // for each token

          let item = {

            "index": (tokenIndex + 1),

            "word": token

          }

          if (typeof(tokenP) == 'function') {

            return tokenP.apply(self, [item]);

          } else {

            return new Promise((resolve, _) => {

              resolve(item);

            });

          }

        });

        Promise.all(tokensP)

          .then(res => {

            resolve({

              index: lineIndex,

              text: sentence,

              tokens: res

            });

          })

          .catch(err => console.error(err))

      });

    });

    Promise.all(sentencesP)

      .then(res => {

        resolve({

          sentences: res

        })

      })

      .catch(err => console.error(err))

  });

} //text2SentencesTokens



// calculate begin and end to each token in a sentence

function calculateTokenBeginEnd(textArray) {

  var currentText = ;

  textArray.sentences.forEach(function(sentence) {

    for (var i = 0; i < sentence.tokens.length; ++i) {

      var token = sentence.tokens[i];

      var word = token.word;

      if (i > 0) {

        var thisBegin = token.characterOffsetBegin;

        var previousEnd = sentence.tokens[i - 1].characterOffsetEnd;

        if (thisBegin > previousEnd) {

          currentText.push(' ');

        }

      }

      token.characterOffsetBegin = currentText.length;

      for (var j = 0; j < word.length; ++j) {

        currentText.push(word[j]);

      }

      token.characterOffsetEnd = currentText.length;

    }

    currentText.push('n');

  });

  return textArray;

} //calculateTokenBeginEnd



text2SentencesTokens(text)

  .then(sentences => {

    sentences = calculateTokenBeginEnd(sentences);

    console.log(sentences);



  })

// convert a text document into a sentences array and a token array for each sentence

function text2SentencesTokens(text, tokenP) {

  var self = this;

  return new Promise((resolve, _) => {

    let sentences = text.split(/n+/g);

    let sentencesP = sentences.map((sentence, lineIndex) => { // for each sentence

      return new Promise((resolve, _) => {

        let tokens = sentence.replace(/[\+;:?!»«><][)(,.‘'“”"]/g, '').split(/s+/g);

        let tokensP = tokens.map((token, tokenIndex) => { // for each token

          let item = {

            "index": (tokenIndex + 1),

            "word": token

          }

          var escaped = token.replace(/[-[]{}()*+?.,\^$|#s]/g, "\$&");

          var wordRegex = RegExp("\b(" + escaped + ")\b", "g");

          var match = null;

          while ((match = wordRegex.exec(text)) !== null) {

            var wordStart = match.index;

            var wordEnd = wordStart + token.length - 1;

            item.characterOffsetBegin = wordStart;

            item.characterOffsetEnd = wordEnd;

          }



          if (typeof(tokenP) == 'function') {

            return tokenP.apply(self, [item, sentence]);

          } else {

            return new Promise((resolve, _) => {

              resolve(item);

            });

          }

        });

        Promise.all(tokensP)

          .then(res => {

            resolve({

              index: lineIndex,

              text: sentence,

              tokens: res

            });

          })

          .catch(err => console.error(err))

      });

    });

    Promise.all(sentencesP)

      .then(res => {

        resolve({

          sentences: res

        })

      })

      .catch(err => console.error(err))

  });

} //text2SentencesTokens



text = "Steve down walks warily down the street downnWith the brim pulled way down low";

text2SentencesTokens(text)

  .then(res => console.log(JSON.stringify(res, null, 2)))

var word = "Lorem";

var reg = RegExp(word, 'g');

var sentence = "Lore ipsum Lorem dolor sit Lorem amet,";

var match;



console.log(sentence);

console.log(word);



while ((match = reg.exec(sentence)) !== null) {

  var wordStart = match.index;

  var wordEnd = wordStart + word.length - 1;

  console.log(wordStart + ' -start index');

  console.log(word.length + ' -length of word');

  console.log(wordEnd + ' -last character index, need to +1 to use with substring');

  console.log(sentence.substring(wordStart, wordEnd + 1) + '-using substring with calculated to find the word and verify');

}